Submission

Put the ipynb file and html file in the github branch you created in the last assignment and submit the link to the commit in brightspace

from plotly.offline import init_notebook_mode
import plotly.io as pio
import plotly.express as px

init_notebook_mode(connected=True)
pio.renderers.default = "plotly_mimetype+notebook"

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

Question 1:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

# Filter the DataFrame to select data for the year 2007
df = px.data.gapminder()
df_2007 = df[df['year']==2007]

# Group the filtered data by continent and calculate the sum of numeric columns
df_2007_new = df_2007.groupby('continent') .agg({'pop': 'sum'}).reset_index()

# Create a bar chart using Plotly Express
df_2007_new_sorted = df_2007_new.sort_values(by='pop', ascending=False)

def format_population(pop):
    if pop < 1e9:
        return f'{pop/1e6:.0f}M'
    else:
        return f'{pop/1e9:.1f}B'

df_2007_new_sorted['pop_text'] = df_2007_new_sorted['pop'].apply(format_population)

fig = px.bar(df_2007_new_sorted, x='pop', y='continent', color='continent',
             color_discrete_map={'Asia': 'blue', 'Africa': 'green', 'Europe': 'red', 'North America': 'purple', 'South America': 'orange', 'Oceania': 'brown'},
             labels={'continent': 'Continent', 'pop': 'Population'},
             text='pop_text')  

# Customize the layout of the chart: hide the legend
fig.update_layout(showlegend=False)

# Update the layout for the y-axis to order categories by total population in ascending order
fig.update_xaxes(categoryorder='total ascending')

# Customize the text labels on the bars: format with two decimal places and position them outside the bars
fig.update_traces(textposition='outside')

# Display the resulting chart
fig.show()

Question 2:

Sort the order of the continent for the visualisation

Hint: Use axis layout setting

# Below are the parts of the code in question 1 that decide the order of the continents:

# df_2007_new_sorted = df_2007_new.sort_values(by='pop', ascending=False)

# fig.update_xaxes(categoryorder='total ascending')

Question 3:

Add text to each bar that represents the population

# Below are the parts of the code in question 1 that create the text on each bar:

# fig = px.bar(df_2007_new_sorted, x='pop', y='continent', color='continent',
             # color_discrete_map={'Asia': 'blue', 'Africa': 'green', 'Europe': 'red', 'North America': 'purple', 'South America': 'orange', 'Oceania': 'brown'},
             # labels={'continent': 'Continent', 'pop': 'Population'},
             # text='pop_text')  
            
# fig.update_traces(textposition='outside')
            

Question 4:

Thus far we looked at data from one year (2007). Lets create an animation to see the population growth of the continents through the years

# Load the Gapminder dataset
df = px.data.gapminder()

# Create a bar chart animation using Plotly Express
fig = px.bar(
    df,
    x="pop",
    y="continent",
    color="continent",
    animation_frame="year",  # Use 'year' as the animation frame
    color_discrete_map={
        'Asia': 'blue',
        'Africa': 'green',
        'Europe': 'red',
        'North America': 'purple',
        'South America': 'orange',
        'Oceania': 'brown',
    },
    labels={'continent': 'Continent', 'pop': 'Population'},
    title='Population Growth by Continent Over Time'
)

# Remove the vertical grid lines
fig.update_traces(selector=dict(type='bar'), marker=dict(line=dict(width=0)))

# Customize the layout of the chart
fig.update_layout(showlegend=False)
fig.update_xaxes(categoryorder='total ascending')

# Display the animated chart
fig.show()

Question 5:

Instead of the continents, lets look at individual countries. Create an animation that shows the population growth of the countries through the years

# Load the Gapminder dataset
df = px.data.gapminder()

# Create a bar chart animation using Plotly Express
fig = px.bar(
    df,
    x="pop",
    y="country",  # Use 'country' instead of 'continent'
    color="country",  # Color by country
    animation_frame="year",  # Use 'year' as the animation frame
    labels={'country': 'Country', 'pop': 'Population'},
    title='Population Growth by Country Over Time'
)

# Customize the layout of the chart
fig.update_layout(showlegend=False)
fig.update_xaxes(categoryorder='total ascending')

# Display the animated chart
fig.show()

Question 6:

Clean up the country animation. Set the height size of the figure to 1000 to have a better view of the animation

# Load the Gapminder dataset
df = px.data.gapminder()

# Create a bar chart animation using Plotly Express
fig = px.bar(
    df,
    x="pop",
    y="country",  # Use 'country' instead of 'continent'
    color="country",  # Color by country
    animation_frame="year",  # Use 'year' as the animation frame
    labels={'country': 'Country', 'pop': 'Population'},
    title='Population Growth by Country Over Time'
)

# Customize the layout of the chart
fig.update_layout(
    showlegend=False,
    height=1000,  # Set the height of the figure to 1000
)

# Display the animated chart
fig.show()

Question 7:

Show only the top 10 countries in the animation

Hint: Use the axis limit to set this.

# Load the Gapminder dataset
df = px.data.gapminder()

# Get the top 10 countries by population for the initial frame (year 1952)
top_10_countries = df[df['year'] == 1952].nlargest(10, 'pop')['country']

# Create a filtered DataFrame containing only the top 10 countries
df_filtered = df[df['country'].isin(top_10_countries)]

# Create a bar chart animation using Plotly Express
fig = px.bar(
    df_filtered,  # Use the filtered DataFrame with only the top 10 countries
    x="pop",
    y="country",  # Use 'country' instead of 'continent'
    color="country",  # Color by country
    animation_frame="year",  # Use 'year' as the animation frame
    labels={'country': 'Country', 'pop': 'Population'},
    title='Top 10 Population Growth by Country Over Time'
)

# Customize the layout of the chart
fig.update_layout(
    showlegend=False,
    height=1000,  # Set the height of the figure to 1000
)

# Set x-axis limits to show the entire range of population values
fig.update_xaxes(range=[0, df['pop'].max()])
fig.update_yaxes(categoryorder='total ascending')

# Display the animated chart
fig.show()